'numpy.ndarray' object has no attribute 'train' - numpy

Question

how can i solve this ? this is my first time for Tensortflow. I try to copy Train and Evaluate the Model from tensortflow tutorial but it seem not work. Can someone help me to solve my problem? Thanks!
http://pastebin.com/NCQKNyKy
import tensorflow as tf
sess = tf.InteractiveSession()
import numpy as np
from numpy import genfromtxt
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 3*3, 1], padding='VALID')
data = genfromtxt('circle_deeplearn_data_small.txt',delimiter=',')
out = genfromtxt('circle_deeplearn_output_small.txt',delimiter=',')
x = tf.placeholder(tf.float32, shape =[None, 3*3*15]) # size of x
y_ = tf.placeholder(tf.float32, shape =[None, 1]) # size of output
W_conv1 = weight_variable([1,3*3,1,15])
b_conv1 = bias_variable([15])
x_image = tf.reshape(x,[-1,1,3*3*15,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
W_fc1 = weight_variable([1 * 1 * 15 , 1])
b_fc1 = bias_variable([1])
h_conv1_flat = tf.reshape(h_conv1 , [-1,1 * 1 * 15])
h_fc1 = tf.nn.relu(tf.matmul(h_conv1_flat , W_fc1) + b_fc1)
y_conv = h_fc1
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#Adam
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#sess.run(tf.global_variables_initializer())
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = data.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={x: data, y_: out, keep_prob: 1.0}))
This is result:
AttributeError: 'numpy.ndarray' object has no attribute 'train'

Answer 1

here datais just a numpy array. You may need to write ur own train data iterator

Answer 2

It is not quite clear what you are trying to do. The problem occurs because data is a numpy array generated in this line
data = genfromtxt('circle_deeplearn_data_small.txt',delimiter=',')
The error occurs when you try to use the method train of data, which does not exist, in the following line
batch = data.train.next_batch(50)
Instead you need to feed data to tensorflow.

Answer 3

I have faced same problem. Actually, it's not a problem. Literally, I didn't know the structure of the data that's why I have faced this problem. Te datasets comes from tensorflow lib are compressed in a single file and separated in a file as train, test, and validation set. That's why when we call dataset.train.next_batch() it does work. You own datatset is not compressed in the same way that's why it doesn't work. You have to configure your dataset on the own way so do the batch system and looping.

Answer 4

You may try to use numpy.reshape to turn your data from 2 dimension into 3 dimension.
For example if you had 20 samples and 100 features, so a (20,100) data matrix and used a minibatch size of 5. Then you could reshape using np.reshape(data,[10,5,-1]) to get a (10,5,40) matrix.
*The "-1" meaning that you leave numpy to count the array for your, the total number of array is 20,000.
Thus, in this example: 10*5*40 = 20,000.